In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 6

Chinese adversarial example generation method based on multi-disturbance strategy

Wang Chundong1,2
Zhu Wenying1,2
Lin Hao1,2
1. School of Computer Science & Engineering, Tianjin University of Technology, Tianjin 300384, China
2. National Engineering Laboratory for Computer Virus Prevention & Control Technology, Tianjin 300384, China
DOI: 10.19734/j.issn.1001-3695.2024.07.0376

Abstract

To address the vulnerability of Deep Neural Networks (DNNs) to adversarial samples and the lack of high-quality adversarial samples in the Chinese context, the method introduces a new Chinese adversarial sample generation method named CMDS. In the keyword selection stage, the Score function used identifies positions where perturbations can be added effectively, ensuring the adversarial samples are both readable and difficult to detect. During the adversarial sample generation phase, the method fully exploits characteristics unique to Chinese, considering aspects such as character shape, meaning, and region-specific homophones. Various perturbation strategies, including similar characters, synonyms, homophones, and word order disruption, are employed along with a multi-priority perturbation strategy to generate adversarial samples. Finally, a perturbation rate threshold controls the output, eliminating samples that differ too greatly from the original text. Following this, a series of experiments compare CMDS with baseline methods to explore the impact of perturbation threshold sizes, involve human evaluations, and conduct real-world attack tests. These experiments confirm the effectiveness and transferability of CMDS in enhancing model security. Results show that CMDS surpasses baseline methods in terms of attack success rate by up to 36.9 percentage points and improves model security by more than 30 percentage points. The generated adversarial samples are of high quality and demonstrate strong generalizability.

Foundation Support

国家自然科学基金联合项目(U1536122)
国家重点研发计划"科技助力经济2020"重点专项(SQ2020YFF0413781)
天津市科委重大专项(15ZXDSGX00030)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.07.0376
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 6

Publish History

[2025-03-10] Accepted Paper

Cite This Article

王春东, 竹文颖, 林浩. 基于多扰动策略的中文对抗样本生成方法 [J]. 计算机应用研究, 2025, 42 (6). (2025-03-10). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0376. (Wang Chundong, Zhu Wenying, Lin Hao. Chinese adversarial example generation method based on multi-disturbance strategy [J]. Application Research of Computers, 2025, 42 (6). (2025-03-10). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0376. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)